[clangd] Fix a subtle case for GetBeginningOfIdentifier.

[sammccall]

Summary

The following case 1 was incorrectly regarded as case 2:

MACRO(foo->^function())

Also add few more tests for macro.

[sammccall]

(Stealing this to make some revisions after pair-programming)

clangd/ClangdUnit.cpp

SourceLocation clangd::getBeginningOfIdentifier(ParsedAST &Unit,
   // We can't actually distinguish cases 1 and 3, but returning the original
   // location is correct for both!
   if (*Offset == 0) // Case 1 or 3.
     return SourceMgr.getMacroArgExpandedLocation(InputLoc);
   SourceLocation Before =
       SourceMgr.getMacroArgExpandedLocation(InputLoc.getLocWithOffset(-1));
   Before = Lexer::GetBeginningOfToken(Before, SourceMgr, AST.getLangOpts());
   Token Tok;
+  // A subtle case 1:
+  //   MACRO(foo->^function())
+  //             ^~~~~~ Before
+  // getRawToken intentionally returns the macro name (whose token is
+  // identifier), we do want the token at Before loc, to achieve that, we pass a
+  // spelling location to getRawToken.
   if (Before.isValid() &&
-      !Lexer::getRawToken(Before, Tok, SourceMgr, AST.getLangOpts(), false) &&
+      !Lexer::getRawToken(SourceMgr.getSpellingLoc(Before), Tok, SourceMgr,
+                          AST.getLangOpts(), false) &&
       Tok.is(tok::raw_identifier))
     return Before;                                        // Case 2.
   return SourceMgr.getMacroArgExpandedLocation(InputLoc); // Case 1 or 3.
 }

unittests/clangd/ClangdUnitTests.cpp

main.cpp:2:3: error: something terrible happened)");
 
   EXPECT_THAT(
       LSPDiags,
       ElementsAre(Pair(EqualToLSPDiag(MainLSP), ElementsAre(EqualToFix(F))),
                   Pair(EqualToLSPDiag(NoteInMainLSP), IsEmpty())));
 }
 
 TEST(ClangdUnitTest, GetBeginningOfIdentifier) {
+  StringRef Common = R"cpp(
+struct Foo { int func(); };
+#define MACRO(X) void f() { X; }
+Foo* foo;
+Foo bar;
+)cpp";
+
   // First ^ is the expected beginning, last is the search position.
   for (const char *Text : {
            "int ^f^oo();", // inside identifier
            "int ^foo();",  // beginning of identifier
            "int ^foo^();", // end of identifier
            "int foo(^);",  // non-identifier
            "^int foo();",  // beginning of file (can't back up)
            "int ^f0^0();", // after a digit (lexing at N-1 is wrong)
            "int ^λλ^λ();", // UTF-8 handled properly when backing up
+
+           // testcases where identifier is in macro.
+           "MACRO(foo->^func())", // beginning of identifier
+           "MACRO(foo->^fun^c())", // inside identifier
+           "MACRO(foo->^func^())", // end of identifier
+           "MACRO(^foo->func())", // begin identifier
+           "MACRO(^foo^->func())", // end identifier
+           "^MACRO(foo->funct())", // beginning of macro name
+           "^MAC^RO(foo->funct())", // inside macro name
+           "^MACRO^(foo->funct())", // end of macro name
        }) {
-    Annotations TestCase(Text);
+    std::string TestCode = (Common + Text).str();
+    Annotations TestCase(TestCode);
     auto AST = TestTU::withCode(TestCase.code()).build();
     const auto &SourceMgr = AST.getASTContext().getSourceManager();
     SourceLocation Actual = getBeginningOfIdentifier(
         AST, TestCase.points().back(), SourceMgr.getMainFileID());
-    Position ActualPos =
-        offsetToPosition(TestCase.code(), SourceMgr.getFileOffset(Actual));
-    EXPECT_EQ(TestCase.points().front(), ActualPos) << Text;
+    Position ActualPos = offsetToPosition(
+        TestCase.code(),
+        SourceMgr.getFileOffset(SourceMgr.getSpellingLoc(Actual)));
+    EXPECT_EQ(TestCase.points().front(), ActualPos) << TestCode;
   }
 }
 
 } // namespace
 } // namespace clangd
 } // namespace clang